Nonrigid registration with corresponding points constraint for automatic segmentation of cardiac DSCT images

Abstract

BackgroundDual-source computed tomography (DSCT) is a very effective way for diagnosis and treatment of heart disease. The quantitative information of spatiotemporal DSCT images can be important for the evaluation of cardiac function. To avoid the shortcoming of manual delineation, it is imperative to develop an automatic segmentation technique for 4D cardiac images.MethodsIn this paper, we implement the heart segmentation-propagation framework based on nonrigid registration. The corresponding points of anatomical substructures are extracted by using the extension of n-dimensional scale invariant feature transform method. They are considered as a constraint term of nonrigid registration using the free-form deformation, in order to restrain the large variations and boundary ambiguity between subjects.ResultsWe validate our method on 15 patients at ten time phases. Atlases are constructed by the training dataset from ten patients. On the remaining data the median overlap is shown to improve significantly compared to original mutual information, in particular from 0.4703 to 0.5015 () for left ventricle myocardium and from 0.6307 to 0.6519 () for right atrium.ConclusionsThe proposed method outperforms standard mutual information of intensity only. The segmentation errors had been significantly reduced at the left ventricle myocardium and the right atrium. The mean surface distance of using our framework is around 1.73 mm for the whole heart.

Simultaneous Multi-Structure Segmentation of the Heart and Peripheral Tissues in Contrast Enhanced Cardiac Computed Tomography Angiography

“…On comparing the computational speed for different multi-atlas methods for automatic CTA segmentation, whereas some groups [8], [9], [14], [17], [29] did not report the computational time, those groups that did [5]- [7], [10], [12], [15], [18] required a much longer processing time (greater than five minutes) than our method (less than three minutes). The processing voxel size is unsurprisingly one of the key factors influencing the overall segmentation time.…”

“…Zheng et al [28] and Baskaran et al [24] segmented the four chambers and the LVM. In Zuluaga et al [7] and Lu et al's [14] works, the four chambers, LVM, and AA were segmented. Cai et al [29] also segmented above six cardiac structures using a Gaussian filter-based method.…”

A Review of 3D-2D Registration Methods and Applications based on Medical Images

“…Registration techniques are widely used in cardiac segmentation and real-time tracking. Lu et al [62] implemented a non-rigid registration-based propagation framework for cardiac segmentation. This method uses the n-dimensional scale-invariant feature transformation method [63] to extract feature point pairs from fixed and motion images, and then achieves automatic segmentation of heart images based on image registration, which effectively reduces the effects of heart motion and boundary blur on segmentation, and the registration effect of this method is shown in Figure 14.…”

An Overview on Image Registration Techniques for Cardiac Diagnosis and Treatment

“…Thus, current advances in image registration techniques have adopted automated cardiac segmentation techniques that can rapidly, objectively, and accurately extract the chamber boundaries from medical images in clinical practice. Among the four chambers, the LV has received the most attention in image registration for cardiac segmentation [ 21 , 57 , 64 , 101 – 110 ]. This is because it plays a key role on the process of blood circulation, and thus, its function/dysfunction is associated with most cardiac diseases.…”